Long-term background memory based on Gaussian mixture model

Abstract

This paper aims to present a long-term background memory framework, which is capable of memorizing long period background in video and rapidly adapting to the changes of background. Based on Gaussian mixture model (GMM), this framework enables an accurate identification of long period background appearances and presents a perfect solution to numerous typical problems on foreground detection. The experimental results with various benchmark sequences quantitatively and qualitatively demonstrate that the proposed algorithm outperforms many GMM-based methods for foreground detection, as well as other representative approaches.

Locally Statistical Dual-Mode Background Subtraction Approach

“…With other specific background scenarios, LSD can successfully detects moving objects, however, the pixel-wise accuracy is unremarkable. In the last experiment, we compare our proposed LSD background subtraction method with several state-of-theart approaches on the Wallflower dataset (i.e., Gaussian Mixture Model (GMM) [12], texture-contained Gaussian Mixture Model (TGMM) [15], Gaussian mixture shadow model (GMSM) [17], memorizing GMM (MGMM) [18], piecewise memorizing GMM (P-MGMM) [20], Lightness-Red-Green-Blue (BF-LRGB) [44]) and on the CDnet2014 dataset (i.e., Gaussian Mixture Model (GMM) [12], improved Gaussian Mixture Model (EGMM) [13], Region-based Mixture of Gaussian (RMoG) [21], Kernel Density Estimation (KDE) [27], Visual Background Subtractor (ViBE) [32], Spatially Coherent Self-Organizing Background Subtraction (SC_SOBS) [36], and Graph Cut algorithm (GraphCut) [39]).…”